{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MVK5WNQYI3DWMUNEZGTGLZZBKB","short_pith_number":"pith:MVK5WNQY","canonical_record":{"source":{"id":"2112.10482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"a40790926c8c8445915e6ef145da09303e9b0c220805b743219fceb151871ec6","abstract_canon_sha256":"6dd25ad7d67a09652bb6000dbb17be5ca34eeefb56ff93f6d49fdd4750728a72"},"schema_version":"1.0"},"canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","source":{"kind":"arxiv","id":"2112.10482","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10482","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10482v3","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10482","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"MVK5WNQYI3DW","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"MVK5WNQYI3DWMUNE","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"MVK5WNQY","created_at":"2026-07-05T04:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MVK5WNQYI3DWMUNEZGTGLZZBKB","target":"record","payload":{"canonical_record":{"source":{"id":"2112.10482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"a40790926c8c8445915e6ef145da09303e9b0c220805b743219fceb151871ec6","abstract_canon_sha256":"6dd25ad7d67a09652bb6000dbb17be5ca34eeefb56ff93f6d49fdd4750728a72"},"schema_version":"1.0"},"canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:08.288373Z","signature_b64":"6vGkvB6bQZDtgxoDWWDUFjWX2aDMDbBbsHJvmSbK3gJSvvf8wNsAim09MNzaYIcOpDkzX7nVy1rgRjBHDiFzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","last_reissued_at":"2026-07-05T04:21:08.287879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:08.287879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.10482","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ku9v744HiJpeDDHrZG4wuvoWU7wqBlDa8TsMROXcdayBPb1MJ8j3KE6cHuNKQ7VcznDFSfJJvUF/0yHR3W++DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:34:06.465584Z"},"content_sha256":"3078913923542dd54fbd37005c015772b24bef6f51b62a6708da708324068802","schema_version":"1.0","event_id":"sha256:3078913923542dd54fbd37005c015772b24bef6f51b62a6708da708324068802"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MVK5WNQYI3DWMUNEZGTGLZZBKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Azuma, Motoaki Kawanabe, Shuhei Kurita, Taiki Miyanishi","submitted_at":"2021-12-20T12:30:55Z","abstract_excerpt":"We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10482","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10482/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhIa2sjuFLWkbdPXfUxmsAH4917+g34ylwpNjzr6EaN4mDNWA/Tuml37LHdl1lCn+40Lx1RrjV75+IDKN2U/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T01:34:06.466428Z"},"content_sha256":"2c73975c0567a2556bf71ee1da870cfa7cd641ded545fff7a2c73e54d8e1e271","schema_version":"1.0","event_id":"sha256:2c73975c0567a2556bf71ee1da870cfa7cd641ded545fff7a2c73e54d8e1e271"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/bundle.json","state_url":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T01:34:06Z","links":{"resolver":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB","bundle":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/bundle.json","state":"https://pith.science/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVK5WNQYI3DWMUNEZGTGLZZBKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MVK5WNQYI3DWMUNEZGTGLZZBKB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6dd25ad7d67a09652bb6000dbb17be5ca34eeefb56ff93f6d49fdd4750728a72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","title_canon_sha256":"a40790926c8c8445915e6ef145da09303e9b0c220805b743219fceb151871ec6"},"schema_version":"1.0","source":{"id":"2112.10482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10482","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10482v3","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10482","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"MVK5WNQYI3DW","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"MVK5WNQYI3DWMUNE","created_at":"2026-07-05T04:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"MVK5WNQY","created_at":"2026-07-05T04:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:2c73975c0567a2556bf71ee1da870cfa7cd641ded545fff7a2c73e54d8e1e271","target":"graph","created_at":"2026-07-05T04:21:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.10482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new 3D spatial understanding task of 3D Question Answering (3D-QA). In the 3D-QA task, models receive visual information from the entire 3D scene of the rich RGB-D indoor scan and answer the given textual questions about the 3D scene. Unlike the 2D-question answering of VQA, the conventional 2D-QA models suffer from problems with spatial understanding of object alignment and directions and fail the object identification from the textual questions in 3D-QA. We propose a baseline model for 3D-QA, named ScanQA model, where the model learns a fused descriptor from 3D object proposals ","authors_text":"Daichi Azuma, Motoaki Kawanabe, Shuhei Kurita, Taiki Miyanishi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10482","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3078913923542dd54fbd37005c015772b24bef6f51b62a6708da708324068802","target":"record","created_at":"2026-07-05T04:21:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6dd25ad7d67a09652bb6000dbb17be5ca34eeefb56ff93f6d49fdd4750728a72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T12:30:55Z","title_canon_sha256":"a40790926c8c8445915e6ef145da09303e9b0c220805b743219fceb151871ec6"},"schema_version":"1.0","source":{"id":"2112.10482","kind":"arxiv","version":3}},"canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6555db361846c76651a4c9a665e721506829452c2f88fbb4e76d261048a08fd7","first_computed_at":"2026-07-05T04:21:08.287879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:08.287879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vGkvB6bQZDtgxoDWWDUFjWX2aDMDbBbsHJvmSbK3gJSvvf8wNsAim09MNzaYIcOpDkzX7nVy1rgRjBHDiFzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:08.288373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.10482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3078913923542dd54fbd37005c015772b24bef6f51b62a6708da708324068802","sha256:2c73975c0567a2556bf71ee1da870cfa7cd641ded545fff7a2c73e54d8e1e271"],"state_sha256":"9c0d760e7fd265cbc26f4fc5c397eb5523d0d549038c76f067b0ffa8754c9680"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wc2jt8rDdhHNySw1WTj5Aqhwb/QzmdscRiEUyx+wcjxzEPTb5ssvdKU0Og0h1Ppd5Pe5lJjBionUVLKdkJfDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T01:34:06.471140Z","bundle_sha256":"31ff707466718f65c7ee1f0ac30d0c78284f87cee2078a2549f84aca16f443e0"}}